secml: Secure and explainable machine learning in Python

We present secml, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including test-time evasion attacks to generate adversarial examples against deep neural networks and training-time poisoning attacks against...

Full description

Saved in:
Bibliographic Details
Published inSoftwareX Vol. 18; p. 101095
Main Authors Pintor, Maura, Demetrio, Luca, Sotgiu, Angelo, Melis, Marco, Demontis, Ambra, Biggio, Battista
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.06.2022
Elsevier
Subjects
Online AccessGet full text
ISSN2352-7110
2352-7110
DOI10.1016/j.softx.2022.101095

Cover

Abstract We present secml, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including test-time evasion attacks to generate adversarial examples against deep neural networks and training-time poisoning attacks against support vector machines and many other algorithms. These attacks enable evaluating the security of learning algorithms and the corresponding defenses under both white-box and black-box threat models. To this end, secml provides built-in functions to compute security evaluation curves, showing how quickly classification performance decreases against increasing adversarial perturbations of the input data. secml also includes explainability methods to help understand why adversarial attacks succeed against a given model, by visualizing the most influential features and training prototypes contributing to each decision. It is distributed under the Apache License 2.0 and hosted at https://github.com/pralab/secml.
AbstractList We present secml, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including test-time evasion attacks to generate adversarial examples against deep neural networks and training-time poisoning attacks against support vector machines and many other algorithms. These attacks enable evaluating the security of learning algorithms and the corresponding defenses under both white-box and black-box threat models. To this end, secml provides built-in functions to compute security evaluation curves, showing how quickly classification performance decreases against increasing adversarial perturbations of the input data. secml also includes explainability methods to help understand why adversarial attacks succeed against a given model, by visualizing the most influential features and training prototypes contributing to each decision. It is distributed under the Apache License 2.0 and hosted at https://github.com/pralab/secml.
ArticleNumber 101095
Author Sotgiu, Angelo
Demontis, Ambra
Demetrio, Luca
Melis, Marco
Biggio, Battista
Pintor, Maura
Author_xml – sequence: 1
  givenname: Maura
  orcidid: 0000-0002-1944-2875
  surname: Pintor
  fullname: Pintor, Maura
  organization: DIEE, University of Cagliari, Via Marengo, Cagliari, Italy
– sequence: 2
  givenname: Luca
  orcidid: 0000-0001-5104-1476
  surname: Demetrio
  fullname: Demetrio, Luca
  organization: DIEE, University of Cagliari, Via Marengo, Cagliari, Italy
– sequence: 3
  givenname: Angelo
  orcidid: 0000-0003-2100-9517
  surname: Sotgiu
  fullname: Sotgiu, Angelo
  organization: DIEE, University of Cagliari, Via Marengo, Cagliari, Italy
– sequence: 4
  givenname: Marco
  orcidid: 0000-0003-3641-2093
  surname: Melis
  fullname: Melis, Marco
  organization: DIEE, University of Cagliari, Via Marengo, Cagliari, Italy
– sequence: 5
  givenname: Ambra
  orcidid: 0000-0001-9318-6913
  surname: Demontis
  fullname: Demontis, Ambra
  organization: DIEE, University of Cagliari, Via Marengo, Cagliari, Italy
– sequence: 6
  givenname: Battista
  orcidid: 0000-0001-7752-509X
  surname: Biggio
  fullname: Biggio, Battista
  email: battista.biggio@unica.it
  organization: DIEE, University of Cagliari, Via Marengo, Cagliari, Italy
BookMark eNqNkNtKw0AQhhep4PEJvMkLtO4x2RW8kOKhUFBQr5fJZqJbtpuySdW-vakRES_UqxkGvv9nvgMyik1EQk4YnTDK8tPFpG3q7m3CKefbCzVqh-xzofi4YIyOvu175LhtF5RSprhWXO4T3aJbhrPsHt06YQaxyvBtFcBHKANmS3DPPmIWEFL08SnzMbvbdM9NPCK7NYQWjz_nIXm8unyY3oznt9ez6cV87CST3Tg3VBWuzjkIVTqjMRecm5xxZBIpVaXOK1CiqGRdKKOhFppJLZjSnEpqjDgksyG3amBhV8kvIW1sA95-HJr0ZCF13gW0KlfCcOzLhJaS5lBiyUAbKPrCstJ9lhyy1nEFm1cI4SuQUbuVaRf2Q6bdyrSDzB4zA-ZS07YJa-t8B51vYpfAhz9Y8YP9X-P5QGFv9sVjsq3zGB1WPqHr-tf9r_w7KmWhBA
CitedBy_id crossref_primary_10_1016_j_inffus_2024_102303
crossref_primary_10_1016_j_cose_2022_103006
crossref_primary_10_1007_s10462_024_11005_9
crossref_primary_10_1016_j_softx_2024_101740
Cites_doi 10.1145/2046684.2046692
10.1109/ACCESS.2019.2909068
10.1016/j.patcog.2018.07.023
10.21105/joss.02607
ContentType Journal Article
Copyright 2022 The Author(s)
Copyright_xml – notice: 2022 The Author(s)
DBID 6I.
AAFTH
AAYXX
CITATION
ADTOC
UNPAY
DOA
DOI 10.1016/j.softx.2022.101095
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
Unpaywall for CDI: Periodical Content
Unpaywall
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2352-7110
ExternalDocumentID oai_doaj_org_article_565392ef62384406abeb1a89a7961bd8
10.1016/j.softx.2022.101095
10_1016_j_softx_2022_101095
S2352711022000656
GroupedDBID 0R~
457
5VS
6I.
AACTN
AAEDW
AAFTH
AALRI
AAXUO
ABMAC
ACGFS
ADBBV
ADEZE
ADVLN
AEXQZ
AFJKZ
AFTJW
AGHFR
AITUG
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
BCNDV
EBS
EJD
FDB
GROUPED_DOAJ
IPNFZ
IXB
KQ8
M~E
O9-
OK1
RIG
ROL
SSZ
AAYWO
AAYXX
ACVFH
ADCNI
AEUPX
AFPUW
AIGII
AKBMS
AKYEP
APXCP
CITATION
ADTOC
UNPAY
ID FETCH-LOGICAL-c414t-69057cf62a35bc98e63229612e14e005b86da537d4f7598af3814831582040993
IEDL.DBID DOA
ISSN 2352-7110
IngestDate Fri Oct 03 12:43:03 EDT 2025
Sun Oct 26 03:47:36 EDT 2025
Tue Jul 01 02:31:34 EDT 2025
Thu Apr 24 23:12:38 EDT 2025
Sun Apr 06 06:53:51 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Security
Explainability
Machine learning
Python3
Adversarial attacks
Language English
License This is an open access article under the CC BY-NC-ND license.
cc-by-nc-nd
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c414t-69057cf62a35bc98e63229612e14e005b86da537d4f7598af3814831582040993
ORCID 0000-0002-1944-2875
0000-0003-3641-2093
0000-0003-2100-9517
0000-0001-7752-509X
0000-0001-9318-6913
0000-0001-5104-1476
OpenAccessLink https://doaj.org/article/565392ef62384406abeb1a89a7961bd8
ParticipantIDs doaj_primary_oai_doaj_org_article_565392ef62384406abeb1a89a7961bd8
unpaywall_primary_10_1016_j_softx_2022_101095
crossref_citationtrail_10_1016_j_softx_2022_101095
crossref_primary_10_1016_j_softx_2022_101095
elsevier_sciencedirect_doi_10_1016_j_softx_2022_101095
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate June 2022
2022-06-00
2022-06-01
PublicationDateYYYYMMDD 2022-06-01
PublicationDate_xml – month: 06
  year: 2022
  text: June 2022
PublicationDecade 2020
PublicationTitle SoftwareX
PublicationYear 2022
Publisher Elsevier B.V
Elsevier
Publisher_xml – name: Elsevier B.V
– name: Elsevier
References Tramèr Florian, Zhang Fan, Juels Ari, Reiter Michael K, Ristenpart Thomas. Stealing machine learning models via prediction APIs. In: 25th USENIX security symposium. 2016, p. 601–18.
Biggio, Nelson, Laskov (b9) 2012
Papernot, Faghri, Carlini, Goodfellow, Feinman, Kurakin (b13) 2018
Shokri, Stronati, Song, Shmatikov (b8) 2017
Demetrio, Biggio (b20) 2021
Sundararajan, Taly, Yan (b17) 2017
Joseph, Nelson, Rubinstein, Tygar (b12) 2018
Biggio, Corona, Maiorca, Nelson, Šrndić, Laskov (b2) 2013; vol. 8190
Ribeiro, Singh, Guestrin (b16) 2016
Papernot, McDaniel, Jha, Fredrikson, Berkay Celik, Swami (b4) 2016
Rauber, Zimmermann, Bethge, Brendel (b19) 2020; 5
Huang L, Joseph AD, Nelson B, Rubinstein B, Tygar JD. Adversarial machine learning. In: 4th ACM workshop on artificial intelligence and security. 2011, p. 43–57.
Szegedy Christian, Zaremba Wojciech, Sutskever Ilya, Bruna Joan, Erhan Dumitru, Goodfellow Ian, et al. Intriguing properties of neural networks. In: International conference on learning representations. 2014.
Rauber Jonas, Brendel Wieland, Bethge Matthias. Foolbox: A Python toolbox to benchmark the robustness of machine learning models. In: Reliable machine learning in the wild workshop, 34th international conference on machine learning. 2017.
Carlini, Wagner (b5) 2017
Gu, Liu, Dolan-Gavitt, Garg (b11) 2019; 7
Nicolae, Sinn, Tran, Buesser, Rawat, Wistuba (b15) 2018
Biggio, Roli (b10) 2018; 84
Melis, Demontis, Biggio, Brown, Fumera, Roli (b22) 2017
Shumailov, Zhao, Bates, Papernot, Mullins, Anderson (b6) 2021
Koh, Liang (b18) 2017
Demontis, Melis, Pintor, Jagielski, Biggio, Oprea (b21) 2019
Melis (10.1016/j.softx.2022.101095_b22) 2017
Koh (10.1016/j.softx.2022.101095_b18) 2017
Demontis (10.1016/j.softx.2022.101095_b21) 2019
Papernot (10.1016/j.softx.2022.101095_b13) 2018
Papernot (10.1016/j.softx.2022.101095_b4) 2016
Sundararajan (10.1016/j.softx.2022.101095_b17) 2017
Carlini (10.1016/j.softx.2022.101095_b5) 2017
Ribeiro (10.1016/j.softx.2022.101095_b16) 2016
Shumailov (10.1016/j.softx.2022.101095_b6) 2021
Nicolae (10.1016/j.softx.2022.101095_b15) 2018
10.1016/j.softx.2022.101095_b7
Biggio (10.1016/j.softx.2022.101095_b2) 2013; vol. 8190
Joseph (10.1016/j.softx.2022.101095_b12) 2018
Rauber (10.1016/j.softx.2022.101095_b19) 2020; 5
Demetrio (10.1016/j.softx.2022.101095_b20) 2021
Gu (10.1016/j.softx.2022.101095_b11) 2019; 7
10.1016/j.softx.2022.101095_b1
Biggio (10.1016/j.softx.2022.101095_b9) 2012
Biggio (10.1016/j.softx.2022.101095_b10) 2018; 84
10.1016/j.softx.2022.101095_b3
Shokri (10.1016/j.softx.2022.101095_b8) 2017
10.1016/j.softx.2022.101095_b14
References_xml – start-page: 3
  year: 2017
  end-page: 18
  ident: b8
  article-title: Membership inference attacks against machine learning models
  publication-title: 2017 IEEE symposium on security and privacy
– start-page: 39
  year: 2017
  end-page: 57
  ident: b5
  article-title: Towards evaluating the robustness of neural networks
  publication-title: IEEE symposium on security and privacy
– year: 2018
  ident: b13
  article-title: Technical report on the cleverhans V2.1.0 Adversarial examples Library
– reference: Tramèr Florian, Zhang Fan, Juels Ari, Reiter Michael K, Ristenpart Thomas. Stealing machine learning models via prediction APIs. In: 25th USENIX security symposium. 2016, p. 601–18.
– volume: 5
  start-page: 2607
  year: 2020
  ident: b19
  article-title: Foolbox native: Fast adversarial attacks to benchmark the robustness of machine learning models in pytorch, tensorflow, and jax
  publication-title: J Open Source Softw
– start-page: 372
  year: 2016
  end-page: 387
  ident: b4
  article-title: The limitations of deep learning in adversarial settings
  publication-title: Proc. 1st IEEE European symposium on security and privacy
– year: 2021
  ident: b20
  article-title: Secml-malware: Pentesting windows malware classifiers with adversarial exemples in python
– reference: Rauber Jonas, Brendel Wieland, Bethge Matthias. Foolbox: A Python toolbox to benchmark the robustness of machine learning models. In: Reliable machine learning in the wild workshop, 34th international conference on machine learning. 2017.
– start-page: 1135
  year: 2016
  end-page: 1144
  ident: b16
  article-title: Why should I trust you?: Explaining the predictions of any classifier
  publication-title: 22nd ACM SIGKDD Int’L Conf. Knowl. Disc. data mining
– reference: Szegedy Christian, Zaremba Wojciech, Sutskever Ilya, Bruna Joan, Erhan Dumitru, Goodfellow Ian, et al. Intriguing properties of neural networks. In: International conference on learning representations. 2014.
– start-page: 1807
  year: 2012
  end-page: 1814
  ident: b9
  article-title: Poisoning attacks against support vector machines
  publication-title: 29th Int’L conf. on machine learning
– year: 2018
  ident: b15
  article-title: Adversarial robustness toolbox v1. 0.0
– year: 2019
  ident: b21
  article-title: Why do adversarial attacks transfer? Explaining transferability of evasion and poisoning attacks
  publication-title: 28th USENIX security symposium USENIX security 19
– start-page: 3319
  year: 2017
  end-page: 3328
  ident: b17
  article-title: Axiomatic attribution for deep networks
  publication-title: International conference on machine learning
– start-page: 212
  year: 2021
  end-page: 231
  ident: b6
  article-title: Sponge examples: Energy-latency attacks on neural networks
  publication-title: 2021 IEEE European symposium on security and privacy
– year: 2018
  ident: b12
  article-title: Adversarial machine learning
– volume: 84
  start-page: 317
  year: 2018
  end-page: 331
  ident: b10
  article-title: Wild patterns: Ten years after the rise of adversarial machine learning
  publication-title: Pattern Recognit
– start-page: 751
  year: 2017
  end-page: 759
  ident: b22
  article-title: Is deep learning safe for robot vision? Adversarial examples against the icub humanoid
  publication-title: ICCVW vision in practice on autonomous robots
– reference: Huang L, Joseph AD, Nelson B, Rubinstein B, Tygar JD. Adversarial machine learning. In: 4th ACM workshop on artificial intelligence and security. 2011, p. 43–57.
– volume: vol. 8190
  start-page: 387
  year: 2013
  end-page: 402
  ident: b2
  article-title: Evasion attacks against machine learning at test time
  publication-title: Machine learning and knowledge discovery in databases
– volume: 7
  start-page: 47230
  year: 2019
  end-page: 47244
  ident: b11
  article-title: Badnets: Evaluating backdooring attacks on deep neural networks
  publication-title: IEEE Access
– start-page: 1885
  year: 2017
  end-page: 1894
  ident: b18
  article-title: Understanding black-box predictions via influence functions
  publication-title: International conference on machine learning
– ident: 10.1016/j.softx.2022.101095_b1
  doi: 10.1145/2046684.2046692
– ident: 10.1016/j.softx.2022.101095_b3
– start-page: 751
  year: 2017
  ident: 10.1016/j.softx.2022.101095_b22
  article-title: Is deep learning safe for robot vision? Adversarial examples against the icub humanoid
– start-page: 39
  year: 2017
  ident: 10.1016/j.softx.2022.101095_b5
  article-title: Towards evaluating the robustness of neural networks
– ident: 10.1016/j.softx.2022.101095_b7
– volume: 7
  start-page: 47230
  year: 2019
  ident: 10.1016/j.softx.2022.101095_b11
  article-title: Badnets: Evaluating backdooring attacks on deep neural networks
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2909068
– start-page: 1885
  year: 2017
  ident: 10.1016/j.softx.2022.101095_b18
  article-title: Understanding black-box predictions via influence functions
– start-page: 1807
  year: 2012
  ident: 10.1016/j.softx.2022.101095_b9
  article-title: Poisoning attacks against support vector machines
– year: 2018
  ident: 10.1016/j.softx.2022.101095_b12
– volume: vol. 8190
  start-page: 387
  year: 2013
  ident: 10.1016/j.softx.2022.101095_b2
  article-title: Evasion attacks against machine learning at test time
– year: 2021
  ident: 10.1016/j.softx.2022.101095_b20
– start-page: 212
  year: 2021
  ident: 10.1016/j.softx.2022.101095_b6
  article-title: Sponge examples: Energy-latency attacks on neural networks
– year: 2018
  ident: 10.1016/j.softx.2022.101095_b15
– volume: 84
  start-page: 317
  year: 2018
  ident: 10.1016/j.softx.2022.101095_b10
  article-title: Wild patterns: Ten years after the rise of adversarial machine learning
  publication-title: Pattern Recognit
  doi: 10.1016/j.patcog.2018.07.023
– year: 2019
  ident: 10.1016/j.softx.2022.101095_b21
  article-title: Why do adversarial attacks transfer? Explaining transferability of evasion and poisoning attacks
– ident: 10.1016/j.softx.2022.101095_b14
– start-page: 1135
  year: 2016
  ident: 10.1016/j.softx.2022.101095_b16
  article-title: Why should I trust you?: Explaining the predictions of any classifier
– year: 2018
  ident: 10.1016/j.softx.2022.101095_b13
– start-page: 3319
  year: 2017
  ident: 10.1016/j.softx.2022.101095_b17
  article-title: Axiomatic attribution for deep networks
– start-page: 3
  year: 2017
  ident: 10.1016/j.softx.2022.101095_b8
  article-title: Membership inference attacks against machine learning models
– volume: 5
  start-page: 2607
  issue: 53
  year: 2020
  ident: 10.1016/j.softx.2022.101095_b19
  article-title: Foolbox native: Fast adversarial attacks to benchmark the robustness of machine learning models in pytorch, tensorflow, and jax
  publication-title: J Open Source Softw
  doi: 10.21105/joss.02607
– start-page: 372
  year: 2016
  ident: 10.1016/j.softx.2022.101095_b4
  article-title: The limitations of deep learning in adversarial settings
SSID ssj0001528524
Score 2.2801383
Snippet We present secml, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning,...
SourceID doaj
unpaywall
crossref
elsevier
SourceType Open Website
Open Access Repository
Enrichment Source
Index Database
Publisher
StartPage 101095
SubjectTerms Adversarial attacks
Explainability
Machine learning
Python3
Security
SummonAdditionalLinks – databaseName: Elsevier Free Content
  dbid: IXB
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEA7Si158i_VFDh4NbTfJbuJNRVFBEVTobclm01LZbpdaUf-9M9lstRcRjzskm2Ty-GbC5BtCjnMJmKczzaSwOUP6FpbprMvwFWMiLM-7Bu8h7-7j62dx25f9JXLRvIXBsMpw9tdnuj-tg6QTtNmpRqPOYwS2Q9JDj8UDKdJuc6EwfcNN__z7nkVGSvrctlieYYWGfMiHeb3CafcBfmIUoaSLeSZ-AJTn8V_AqeW3sjKf76YofuDQ1TpZDQYkPav7uEGWXLlJ1prkDDTs1S2iXp0dF6fUX6g7asqcuo-qCI-l6NgHUToaskYM6aikD59IJLBNnq8uny6uWUiTwKzoiRkD_1YmdhBHhsvMauVi2KQaLBfXEw42Wabi3Eie5GKQSK3MAEBaKN6TAP7g3Wm-Q1rlpHS7hCZd7WI7QI4xAXaUNLlUijsJAi25TdokanST2sAhjqksirQJFntJvUJTVGhaK7RNTuaVqppC4_fi56j0eVHkv_aCyXSYhgWQSmTUjRwMmisBNonJAHOM0iaBgWe5apO4mbJ0YTnBr0a_t87mE_yX3u79t6F9soJfddTZAWnNpm_uEOybWXbkF_AXDiDyeg
  priority: 102
  providerName: Elsevier
– databaseName: Unpaywall
  dbid: UNPAY
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aD56sT6yo5ODR7WM32U28qSgiWApaUC9LXluq61q0xeqvd5LNlopQ9Bpmk81MkvkmTL5B6EhT8Hlc8oASpQNL3xJILtuBfcWYEBXptrD3kDfd-KpPru_pvS_15bMq3-H8mXpNurPa67B1GwJaSDo2RnGuM26NdLaMVmIKMLyGVvrd3umDKyZHATWCXMUy5PK5XLcQEIahbWnbghJznsgR9v9wSKuTYiQ-P0Sezzmcyzp6rJ7tlHkmz83JWDbV128Wx__PZR2teRiKT0u5DbRkik1Ur0o8YL_jtxB7N-olP8HuWt5gUWhspqPcP7nCLy4V02Bfe2KAhwXufVo6gm3Uv7y4O78KfLGFQJEOGQcQJdNEZXEoIioVZyaGrc4B_5gOMbBVJYu1oFGiSZZQzkQGrp6wqEMBQkCMyKMdVCteC7OLcNLmJlaZZSojgMao0JSxyFBo4DRSSQOFleJT5ZnIbUGMPK1Szp5Sp7jUWistrdVAx7OPRiURx2LxM2vRmahl0XYNr2-D1BshpZaXNzQw6YgRQDZCgucSjIsEJi41a6C4Wg-pByQl0ICuhotHD2ar5y9_u_dP-X1UG79NzAHgobE89Cv_G-LTBuM
  priority: 102
  providerName: Unpaywall
Title secml: Secure and explainable machine learning in Python
URI https://dx.doi.org/10.1016/j.softx.2022.101095
http://www.softxjournal.com/article/S2352711022000656/pdf
https://doaj.org/article/565392ef62384406abeb1a89a7961bd8
UnpaywallVersion publishedVersion
Volume 18
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 2352-7110
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0001528524
  issn: 2352-7110
  databaseCode: KQ8
  dateStart: 20150901
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2352-7110
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0001528524
  issn: 2352-7110
  databaseCode: DOA
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVESC
  databaseName: Elsevier Free Content
  customDbUrl:
  eissn: 2352-7110
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0001528524
  issn: 2352-7110
  databaseCode: IXB
  dateStart: 20150901
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2352-7110
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0001528524
  issn: 2352-7110
  databaseCode: M~E
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVLSH
  databaseName: Elsevier Journals
  customDbUrl:
  mediaType: online
  eissn: 2352-7110
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0001528524
  issn: 2352-7110
  databaseCode: AKRWK
  dateStart: 20150901
  isFulltext: true
  providerName: Library Specific Holdings
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQGWDhjSiPygMjFmliJzZbi6gKFVWFqChT5DguKkpDRVvR_nvOTlKFpTCwZDgljnU--7uz7r5D6DJmgHkiEoRRFRND30IiETnEVDEGVHmxI8095GPXb_fpw4ANSq2-TE5YRg-cKe6aGe5UVw8BpjkF9JERnC6SCxkIvx7FtszX4aIUTGX1wS5ntqOtCx4GCQDkCsohm9w1hTNuAdGh6xqJY7pLlGDJsvf_QKeteTqRyy-ZJCX0ae2hndxtxI1suvtoQ6cHaLdoyYDzHXqI-FSrcXKD7TW6xjKNsV5MkrxECo9t6qTGea-INzxKcW9p6AOOUL9193zbJnlzBKJonc4IRLUsUKAW6bFICa592JqgElfXqYatFXE_lswLYjoMmOByCNBMuVdnAPkQ0wnvGFXSj1SfIBw4QvtqaJjFKHhPTMaMc08zEAjmqaCK3EI3ocqZw00DiyQsUsTeQ6vQ0Cg0zBRaRVerjyYZccb615tG6atXDeu1FYAthLkthL_ZQhX5xZKFuQOROQYw1Gj938lqgf8y29P_mO0Z2jZDZnln56gy-5zrC_BwZlENbTY6Ty-dmjVqeN4PmiDrd3uN128cufWV
linkProvider Directory of Open Access Journals
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dT9swED8x9gAvDAaIwhh-4HFW28RObN4GGuo2QJMGUt8sx3FRUQgVtKL899w5ToEXNO31Ysf22b4P6-53AIelRJ2nC82lcCUn-BZe6KLHKYsxFy4te5beIc8vssGV-DWUwyU4aXNhKKwyyv5GpgdpHSndyM3uZDzu_k3Qdsj75LEERZp9gI9ConVCWXzD45eHFpkoGYrbUgdOPVr0oRDn9YDibo6OYpIQpUeFJl5pqADk_0ZRrczqiX16tFX1ShGdrsNatCDZ92aSG7Dk68_wqa3OwOJl3QT14N1tdcTCi7pnti6Zn0-qmC3FbkMUpWexbMQ1G9fszxMhCWzB1emPy5MBj3USuBN9MeXo4MrcjbLEprJwWvkMb6lG08X3hcdbVqistDLNSzHKpVZ2hFpaqLQvUfuje6fTbViu72q_AyzvaZ-5EYGMCTSkpC2lUqmXSNAydXkHkpY3xkUQcaplUZk2WuzGBIYaYqhpGNqBb4tOkwZD4_3mx8T0RVMCwA6Eu_trE0-AkQSpm3hcdKoEGiW2QKVjlbY5LrwoVQeydsvMm_OEvxq_PzpfbPC_zHb3fwc6gJXB5fmZOft58XsPVulLE4L2BZan9zO_j8bOtPgaDvMzWkX1oA
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aD56sT6yo5ODR7WM32U28qSgiWApaUC9LXluq61q0xeqvd5LNlopQ9Bpmk81MkvkmTL5B6EhT8Hlc8oASpQNL3xJILtuBfcWYEBXptrD3kDfd-KpPru_pvS_15bMq3-H8mXpNurPa67B1GwJaSDo2RnGuM26NdLaMVmIKMLyGVvrd3umDKyZHATWCXMUy5PK5XLcQEIahbWnbghJznsgR9v9wSKuTYiQ-P0Sezzmcyzp6rJ7tlHkmz83JWDbV128Wx__PZR2teRiKT0u5DbRkik1Ur0o8YL_jtxB7N-olP8HuWt5gUWhspqPcP7nCLy4V02Bfe2KAhwXufVo6gm3Uv7y4O78KfLGFQJEOGQcQJdNEZXEoIioVZyaGrc4B_5gOMbBVJYu1oFGiSZZQzkQGrp6wqEMBQkCMyKMdVCteC7OLcNLmJlaZZSojgMao0JSxyFBo4DRSSQOFleJT5ZnIbUGMPK1Szp5Sp7jUWistrdVAx7OPRiURx2LxM2vRmahl0XYNr2-D1BshpZaXNzQw6YgRQDZCgucSjIsEJi41a6C4Wg-pByQl0ICuhotHD2ar5y9_u_dP-X1UG79NzAHgobE89Cv_G-LTBuM
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=secml%3A+Secure+and+explainable+machine+learning+in+Python&rft.jtitle=SoftwareX&rft.au=Maura+Pintor&rft.au=Luca+Demetrio&rft.au=Angelo+Sotgiu&rft.au=Marco+Melis&rft.date=2022-06-01&rft.pub=Elsevier&rft.issn=2352-7110&rft.eissn=2352-7110&rft.volume=18&rft.spage=101095&rft_id=info:doi/10.1016%2Fj.softx.2022.101095&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_565392ef62384406abeb1a89a7961bd8
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2352-7110&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2352-7110&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2352-7110&client=summon